Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The pawn shop door clanged shut behind her, the sound echoing in the stale air. A sense of weary resignation settled over her, a heavy shroud she couldn’t seem to shake. The job interview had gone badly. Her bills were overdue. The future stretched before her, a vast and intimidating wasteland. She felt… subdued.

She ran a hand through her hair, her fingers tangling in the strands. The shop was a collection of lost hopes and forgotten dreams. She felt a sense of melancholy as she looked at the items in the display cases.

Suddenly, her vision narrowed. Her grandmother's ring. Nestled between a chipped teacup and a broken music box, there it was. She felt a cold dread creep through her, a chilling reminder of all that had been and all that was lost.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

This story is one of 1,000 stories generated for the emotion dispirited. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 dispirited stories, after denoising with neutral dialogue baselines, produces the dispirited emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the dispirited vector is projected through the unembedding matrix.

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240